How to Use the Kingdee / 金蝶 MCP in AutoGen

Q: How do I connect Kingdee / 金蝶 to AutoGen?

Install the autogen-extmcp package. Initialize your tools using mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting list directly into your AssistantAgent.

Q: How does AutoGen handle Kingdee / 金蝶 API errors?

Agents discuss the failure. If submitform returns a validation error, the execution agent shares the error log. The drafting agent revises the payload and tries again.

Q: Can agents delete records if they make a mistake?

If you grant them the deleteform tool. A cleanup agent can wipe duplicate or malformed records after the primary agents finish their debate.

Build multi-agent AutoGen systems that debate and execute Kingdee ERP workflows automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kingdee / 金蝶 MCP to AutoGen

Create your Vinkius account to connect Kingdee / 金蝶 to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kingdee / 金蝶 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven approvals

High-stakes ERP decisions shouldn't rely on a single prompt. You build systems where specialized agents debate the validity of a transaction before acting. A compliance agent reviews the details via `view_form`. A financial agent argues against the spend. They negotiate. Only when they reach consensus does the execution agent trigger `audit_form`—or `un_audit_form` if they spot a violation.

Multi-agent data entry via MCP Server

Data entry gets messy when humans make typos. Your agents handle the entire drafting process by challenging each other's work through the MCP Server. One agent drafts the material request using `save_form`. A second agent verifies the required fields. Once the draft passes inspection, the first agent executes `submit_form` and updates the workflow via `status_convert`.

Navigating complex hierarchies

Agents need to know who owns what. They pull organizational structures dynamically to route tasks to the right department. The team leader agent runs `get_org_info` to map the corporate hierarchy. It assigns data gathering tasks to worker agents, who execute `query_data` and `list_forms`. They compile the findings and present a unified report.

Setup guide

Set up Kingdee / 金蝶 MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kingdee / 金蝶 tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kingdee / 金蝶_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kingdee / 金蝶 data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kingdee / 金蝶_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kingdee / 金蝶 data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kingdee / 金蝶. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kingdee / 金蝶 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kingdee / 金蝶 MCP in AutoGen

Install the autogen-ext[mcp] package. Initialize your tools using mcp_server_tools with a StreamableHttpServerParams configuration. Pass the resulting list directly into your AssistantAgent.

Yes. You can assign different tools to different agents. The finance agent gets audit_form while the inventory agent gets save_form. They collaborate to complete complex business flows.

Agents discuss the failure. If submit_form returns a validation error, the execution agent shares the error log. The drafting agent revises the payload and tries again.

If you grant them the delete_form tool. A cleanup agent can wipe duplicate or malformed records after the primary agents finish their debate.

Extremely secure. The connection runs through an isolated V8 sandbox. Your corporate hierarchy, vendor lists, and financial queries process in memory and destroy instantly once the agents finish their task.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript